Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases associated with quality and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Best" or "worst" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    best of / worst of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ylvanian
    -0.51
    Composable
    -0.48
    +#+#
    -0.47
     entendu
    -0.46
     arché
    -0.46
     Herald
    -0.45
     brukt
    -0.44
    malink
    -0.44
     مشين
    -0.43
     мной
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.88
     offered
    0.80
     ditawarkan
    0.77
    principalTable
    0.75
     ModelExpression
    0.73
     MainAxisSize
    0.70
    offered
    0.68
    AndEndTag
    0.66
     ContentValues
    0.63
     available
    0.63
    Act Density 0.144%

    No Known Activations